Abilityai/cornelius

AI-powered second brain template for Claude Code + Obsidian

This repository also configures its own agents. See what cornelius tells them →

106Stars on the repository
78Mods indexed here, across every type
14d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

incubation-loop

25

Abilityai/cornelius

Skill Claude Code needs its repo

Autonomous iterative thinking loop - processes active topics using rotating analytical moves (ACH, Bayesian updating, steelmanning, cross-domain bridging, implication checks) and persists reasoning state across scheduled runs.

not rated 106 +2 14d ago A 42 tokens original MIT

ingest-source

26

Abilityai/cornelius

Skill Claude Code

Fully autonomous end-to-end ingestion of a SINGLE source (book, paper, article, transcript) into the knowledge base - prepare to markdown, extract insights against the live index, refresh the index, auto-link to existing knowledge, and changelog. One source per invocation.

not rated 106 +2 14d ago A 58 tokens original MIT

Abilityai/cornelius

Skill Claude Code

Standard format for capturing and documenting insights in the knowledge base. Use when harvesting insights, creating permanent notes from user perspectives, or documenting unique thinking patterns.

not rated 106 +2 14d ago A 36 tokens original MIT

insight-interview

28

Abilityai/cornelius

Skill Claude Code

KB-grounded Socratic interview. Searches existing notes on a topic, then runs a one-question-at-a-time dialogue to surface, sharpen, and extract your own thinking. Ends by running extract-insights on the full conversation transcript.

not rated 106 +2 14d ago A 52 tokens original MIT

Abilityai/cornelius

Skill Claude Code

Find notes created in the last 14 days and discover their connections to the knowledge base.

not rated 106 +2 14d ago A 24 tokens original MIT

learn-new-things

30

Abilityai/cornelius

Skill Claude Code

Continuous learning heartbeat - autonomously researches, extracts insights, and expands knowledge base.

not rated 106 +2 14d ago A 20 tokens original MIT

Abilityai/cornelius

Skill Claude Code needs its repo

Upsert and maintain entity notes in a REFERENCE-kind scope (external facts/records), then reindex so they become connection/insight targets. Generic across reference scopes; Company is the default. The scope's entity taxonomy (type/relationship) lives in that scope's own schema doc (Company's is…

not rated 106 +2 14d ago A 88 tokens original MIT

Abilityai/cornelius

Skill Claude Code needs its repo

Manage the incubation loop topic lifecycle — seed new questions, review status, crystallize converged conclusions, and retire stale topics.

not rated 106 +2 14d ago A 29 tokens original MIT

Abilityai/cornelius

Skill Claude Code

Manage domain-watch surveillance configs — seed new domains, review scan status and proposals, activate Watch Log proposals into thinking topics, pause domains, and update PIRs or watch queries.

not rated 106 +2 14d ago A 40 tokens original MIT

Abilityai/cornelius

Skill Claude Code

Extract chapters from PDF, MOBI, and AZW3 book files into individual markdown files. Use when extracting non-EPUB books. PDF uses pymupdf with TOC-based chapter splitting and auto-OCR fallback (Gemini) for scanned/image-only PDFs; MOBI/AZW3 routes through calibre then epub-chapter-extractor.

not rated 106 +2 14d ago A 75 tokens original MIT

Abilityai/cornelius

Skill Claude Code

Generate images using Google's Nano Banana (Gemini 2.5 Flash Image). Use when creating infographics, diagrams, thumbnails, social media graphics, or any AI-generated images. Costs $0.039/image.

not rated 106 +2 14d ago A 49 tokens original MIT

propagate-change

36

Abilityai/cornelius

Skill Claude Code needs its repo

Propagate staleness from a changed note through the Brain Dependency Graph - shows which downstream notes need review.

not rated 106 +2 14d ago A 25 tokens original MIT

quick-search

37

Abilityai/cornelius

Skill Claude Code

Fast knowledge base retrieval - single FAISS search + graph connections, no subagents or LLM orchestration.

not rated 106 +2 14d ago A 24 tokens original MIT

recall

38

Abilityai/cornelius

Skill Claude Code

Retrieve relevant knowledge from Obsidian vault using 3-layer semantic search based on conversation context.

not rated 106 +2 14d ago A 21 tokens original MIT

ref-audit

39

Abilityai/cornelius

Skill Claude Code

Integrity report for a reference scope — the reference-scope analog of /coherence-sweep. Scans every entity note for provenance violations (any note not provenance:reference), type/relationship enum violations, missing/invalid asof, status/supersededby integrity, dangling wiki-links, orphan entities, and…

not rated 106 +2 14d ago A 101 tokens original MIT

ref-bridge

40

Abilityai/cornelius

Skill Claude Code

Bridge reference entities to the cognitive knowledge base — "this client maps to that insight you had." A thin mode over connection-finder that mounts core,Company/ and surfaces entity↔insight bridges, making the reference scope more than a CRM. READ-ONLY sense — it surfaces candidate bridges for human consideration…

not rated 106 +2 14d ago A 94 tokens original MIT

ref-ingest

41

Abilityai/cornelius

Skill Claude Code needs its repo

The single entry point for incoming information of ANY kind about a reference entity (a person, org, product, engagement, or watched competitor). Extracts entity facts, RESOLVES them to the one existing canonical note (never duplicating), reconciles new-vs-old, and upserts (overwrite body, re-stamp asof, append Change…

not rated 106 +2 14d ago A 128 tokens original MIT

ref-query

42

Abilityai/cornelius

Skill Claude Code

Structured, temporal lookup against a reference scope — "what do we know about Acme Corp as of today?", "which engagements are active and expiring in 90 days?", "list our competitors". Respects status (active over superseded), validity windows, and asof freshness, and ALWAYS prints the asof date so staleness is…

not rated 106 +2 14d ago A 96 tokens original MIT

ref-reconcile

43

Abilityai/cornelius

Skill Claude Code

Keep a reference scope canonical and internally consistent. SENSE phase (auto) detects issues by invoking ref-audit; FIX phase (human-gated) resolves conflicts, repairs bidirectional link integrity (A cites [[B]] as client → does B back-link?), fixes/removes dangling links, and MERGES duplicate entities into one…

not rated 106 +2 14d ago A 94 tokens original MIT

ref-refresh

44

Abilityai/cornelius

Skill Claude Code

Mechanical staleness sweep over a reference scope. Scans every note's asof age against the per-type Freshness SLA, builds an overdue-sorted refresh queue, then splits by scope — market/ stale items are handed to ref-ingest (the gate-free overwrite branch) for autonomous re-verification; CRM stale items are report-only…

not rated 106 +2 14d ago A 87 tokens original MIT

ref-supersede

45

Abilityai/cornelius

Skill Claude Code

Handle a validity transition on a reference entity — a contract renewal, role change, or re-termed price where a full prior snapshot matters. Creates the new status:active note (with validfrom/validuntil), marks the old note status:superseded + supersededby:[[New]], keeps both for history, and reindexes. Human-gated.…

not rated 106 +2 14d ago A 113 tokens original MIT

refresh-index

46

Abilityai/cornelius

Skill Claude Code

Rebuild the Local Brain Search FAISS index to reflect vault changes.

not rated 106 +2 14d ago A 16 tokens original MIT

scheduled-run

47

Abilityai/cornelius

Skill Claude Code

Wrapper for scheduled playbooks - handles git sync before and after execution.

not rated 106 +2 14d ago A 16 tokens original MIT

search-vault

48

Abilityai/cornelius

Skill Claude Code

Quick search across Obsidian vault using keywords or semantic similarity.

not rated 106 +2 14d ago A 16 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: